Agent skill · Audited from source
dogfood
skill · nousresearch/hermes-agentMIT licenceAudited 14 Nov 2026 · source b42117873683
Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit b42117873683 and found no filesystem, network or shell access and no hard-coded secrets. What it does: Exploratory QA of web apps: find bugs, evidence, reports.
Cite
Cite this page
ModelsAtlas. “dogfood (nousresearch/hermes-agent)”. Retrieved 14 Nov 2026. https://modelsatlas.com/skills/nousresearch/dogfood
3 skills are called “dogfood”. You are viewing nousresearch/hermes-agent.
- nousresearch/hermes-agent★ 263k✓SAFE
- callstack/agent-device★ 5.1k✓SAFE
- callstackincubator/agent-device★ 5.1k✓SAFE
Trust audit
Audit 0.4.1 · source read 14 Nov 2026
SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 17,406 of 18,389 audited skills.
What the source does
- FilesystemNone observedNo reads or writes in the source
- NetworkNone observedNo outbound calls in the source
- ShellNone observedNo commands run in the source
- DependenciesPinnedNothing floats
- SecretsNone foundNo keys in source
Five audit layers
| Layer | What we check | Result | Findings |
|---|---|---|---|
L0 Provenance | Repo owner, licence, archive status, activity | PASS | 0 |
L1 Static source | Secrets, path traversal, supply chain, hidden code | NA | 0 |
L2 Instructions | Prompt injection, authority framing, hidden directives | PASS | 0 |
L3 Inventory | The files and declarations match the source | PASS | 0 |
L4 Sandbox | Run in isolation and watch behaviour | SKIPPED why | 0 |
Gates applied: no behavioural pass.
Findings (0)
No findings at any severity. We re-audit when the source changes.
Audit 0.4.1 · source sha b42117873683 · 14 Nov 2026Report an issue or request a re-scan
Provenance
Who published it, and what the verdict is pinned to
- Publishernousresearch GitHub organizationOwner of the repository this skill is read from
- Source foldernousresearch/hermes-agent/skills/software-development/dogfoodThe exact folder we audited
- LicenceMITAs the repository states it
- Commit pinned for this verdictb42117873683A new audit runs when the source changes
- Repository statusNot archivedPushed today
- Sandboxed runNot runSkills are read, not executed; layer L4 is skipped
What it tells the agent
Full source on GitHub ↗Its description: Exploratory QA of web apps: find bugs, evidence, reports.
---
name: dogfood
description: "Exploratory QA of web apps: find bugs, evidence, reports."
version: 1.0.0
author: Teknium (teknium1), Hermes Agent
license: MIT
platforms: [linux, macos, windows]
metadata:
hermes:
tags: [qa, testing, browser, web, dogfood]
related_skills: []
---
# Dogfood: Systematic Web Application QA Testing
## Overview
This skill guides you through systematic exploratory QA testing of web applications with `browser_exec`. You will navigate the application, interact with elements, capture evidence of issues, and produce a structured bug report.
## Prerequisites
- The `browser` toolset must be enabled (`browser_exec`). `browser_exec` runs Python with pre-imported helpers (`new_tab`, `goto_url`, `wait_for_load`, `page_info`, `js`, `fill_input`, `click_at_xy`, `capture_screenshot`, `cdp`); browser state persists across calls, Python variables do not.
- A target URL and testing scope from the user
## Inputs
The user provides:
1. **Target URL** — the entry point for testing
2. **Scope** — what areas/features to focus on (or "full site" for comprehensive testing)
3. **Output directory** (optional) — where to save screenshots and the report (default: `./dogfood-output`)
## Workflow
Follow this 5-phase systematic workflow:
### Phase 1: Plan
1. Create the output directory structure:
```
{output_dir}/
├── screenshots/ # Evidence screenshots
└── report.md # Final report (generated in Phase 5)
```
2. Identify the testing scope based on user input.
3. Build a rough sitemap by planning which pages and features to test:
- Landing/home page
- Navigation links (header, footer, sidebar)
- Key user flows (sign up, login, search, checkout, etc.)
- Forms and interactive elements
- Edge cases (empty states, error pages, 404s)
### Phase 2: Explore
Batch each step's actions into one `browser_exec` call. For each page or feature in your plan:
1. **Navigate with a console hook installed.** Register the hook on the tab before navigating so errors thrown during page load are captured too:
```python
# Open page with console-error capture
HOOK = """window.__qa_errors = [];
const _e = console.error;
console.error = (...a) => { window.__qa_errors.push(a.map(String).join(' ')); _e(...a); };
addEventListener('error', e => window.__qa_errors.push('uncaught: ' + e.message));
addEventListener('unhandledrejection', e => window.__qa_errors.push('rejection: ' + String(e.reason)));"""
new_tab('about:blank') # first call only: the hook binds to the current tab
cdp('Page.addScriptToEvaluateOnNewDocument', source=HOOK)
goto_url("https://example.com/page")
wait_for_load()
print(page_info())
print(js('window.__qa_errors || []'))
```
Re-register the hook at the start of any later call that navigates. Silent JS errors are high-value findings.
2. **Read the page structure** — list visible interactive elements with their viewport centres (use `cdp('Accessibility.getFullAXTree')` and filter in Python when you need roles/names):
```python
# List interactive elements
print(js("""(() => [...document.querySelectorAll('a,button,input,select,textarea,[role=button]')]
.filter(e => e.offsetParent).slice(0, 80).map((e, i) => { const r = e.getBoundingClientRect();
return {i, tag: e.tagName, text: (e.innerText || e.value || e.getAttribute('aria-label') || '').trim().slice(0, 60),
id: e.id, name: e.name, x: Math.round(r.x + r.width / 2), y: Math.round(r.y + r.height / 2)}; }))()"""))
```
3. **Visually assess the page:** call `capture_screenshot()` and inspect the attached image for layout issues, broken elements, or accessibility concerns. If your model cannot view images, pass the printed path to `vision_analyze`.
4. **Test interactive elements** systematically:
- Click buttons and links: `js("document.querySelector('#submit').click()")`, or `click_at_xy(x, y)` with a centre from step 2
- Fill forms: `fill_input('input[name=email]', 'test input')`
- Test keyboard navigation: `cdp('Input.dispatchKeyEvent', type='keyDown', key='Tab', code='Tab', windowsVirtualKeyCode=9)` followed by the matching `keyUp`, then `js('document.activeElement.outerHTML.slice(0, 200)')` to see where focus landed; same pattern with `key='Enter'`, `code='Enter'`, `windowsVirtualKeyCode=13`
- Scroll through content: `js('window.scrollBy(0, 800)')`
- Go back: `js('history.back()')`, then `wait_for_load()`
- Test form validation with invalid inputs
- Test empty submissions
5. **After each interaction**, in the same call, check for:
- Console errors: `print(js('window.__qa_errors || []'))`
- Visual changes: `capture_screenshot()` and compare with the previous one
- Expected vs actual behavior (`page_info()`, or `js()` reading the relevant element)
### Phase 3: Collect Evidence
For every issue found:
1. **Take a screenshot** showing the issue: `capture_screenshot()` prints the saved path. Copy it to `{output_dir}/screenshots/` under a descriptive name (e.g. `issue-03-broken-login.png`) — you will reference it in the report.
2. **Record the details**:
- URL where the issue occurs
- Steps to reproduce
- Expected behavior
- Actual behavior
- Console errors (if any)
- Screenshot path
3. **Classify the issue** using the issue taxonomy (see `references/issue-taxonomy.md`):
- Severity: Critical / High / Medium / Low
- Category: Functional / Visual / Accessibility / Console / UX / Content
### Phase 4: Categorize
1. Review all collected issues.
2. De-duplicate — merge issues that are the same bug manifesting in different places.
3. Assign final severity and category to each issue.
4. Sort by severity (Critical first, then High, Medium, Low).
5. Count issues by severity and category for the executive summary.
### Phase 5: Report
Generate the final report using the template at `templates/dogfood-report-template.md`.
The report must include:
1. **Executive Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.
Install
Pinned to the audited commit b421178
git clone https://github.com/nousresearch/hermes-agent git -C hermes-agent checkout b42117873683
The author documents no install command, so this uses the repository directly. Our verdict covers commit b42117873683 only.
Works in
The author has not said which agents this skill supports, and we have not tested it in any.
Audit history
Every audit, every source change
- ✓SAFE B 89 / 100
first audit · source
b42117873683
README badge
For maintainers · shows the latest audit
[](https://modelsatlas.com/skills/nousresearch/dogfood/)
The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.
Similar skills
nousresearch/hermes-agent
Author/validate/export Google's DESIGN.md token spec files.
nousresearch/hermes-agent
Generate images, video, and audio via diffusion workflows.
nousresearch/hermes-agent
Design one-off HTML artifacts (landing, deck, prototype).
nousresearch/hermes-agent
Delegate coding to OpenAI Codex CLI (features, PRs).
nousresearch/hermes-agent
Monitor blogs and RSS/Atom feeds via blogwatcher-cli tool.
nousresearch/hermes-agent
ASCII video: convert video/audio to colored ASCII MP4/GIF.
Add this badge to your README
[](https://modelsatlas.com/skills/nousresearch/dogfood/)
<a href="https://modelsatlas.com/skills/nousresearch/dogfood/"><img src="https://modelsatlas.com/skills/nousresearch/dogfood/badge.svg" alt="ModelsAtlas: SAFE B"></a>
Questions about dogfood
What does the dogfood skill do?
Is dogfood safe to install?
What can dogfood access on my machine?
How current is this page?
Sources
- github.com/nousresearch/hermes-agent/tree/main/skills/software-d — the audited source at commit b42117873683 and every finding aboveObserved · 14 Nov 2026
Spotted something wrong? Report a correction · Methodology
Keep going in your AI
Opens with this page as the source. We add nothing else to the prompt.
- What does the dogfood skill do?
- Is dogfood safe to install?
- What can dogfood access on my machine?